Min
Max
Min
Max
Min
Max
Min
Max
Related Objects of Interest: writing , standing , walking , sitting , sleeping , hand-raising , listening , filing , reclining , typing
1 - 50 of 500k+
Top Reading Computer Vision Models
The models below have been fine-tuned for various reading detection tasks. You can try out each model in your browser, or test an edge deployment solution (i.e. to an NVIDIA Jetson). You can use the datasets associated with the models below as a starting point for building your own reading detection model.
At the bottom of this page, we have guides on how to count readings in images and videos.
4.2k images 18 classes 2 models
130 images 10 classes 1 model
1k images 7 classes 1 model
4.4k images 54 classes 3 models
object "Wailing Meer Trees" in front of Seodaemun Prison where Japanese executed Korean independence fighters 1 2 4 6 7 Chinese English Footsteps in the struggle for justice Japan's tool for torture of the Korean people Japanese Korean Korean Cinnamon rice cake Korean Independence Gate Korean flag Korean independence fighters tortured by Japanese imperialism Korean independence fighters trapped in prison while fighting against Japanese imperialism Korean mugwort bean rice cake Korean original Bean Cake
205 images 6 classes 4 models
140 images 8 classes 1 model
2.3k images 5 classes 1 model
372 images 9 classes 1 model
2.9k images 5 classes 1 model
9.9k images 5 classes 1 model
71 images 12 classes 2 models
110 images 109 classes 1 model
A German Shepherd chases another with a stick in his mouth A Group of men firing an old fashion cannon A black and white bird eating seeds out of someone 's hand A black and white dog stands on the grass with a baseball in his mouth A black dog nurses white puppies . A boy dressed in soccer attire and holding his shoes getting out of a car . A boy hits a ball off of a tee ball into to net . A boy in his blue swim shorts at the beach . A boy in yellow is riding a scooter on the street A boy in yellow shorts is standing on top of a cliff . A boy wearing a red shirt and jeans is doing a flip on his bike A boy with a stick kneeling in front of a goalie net A brown dog biting a gray dogs ear . A brown dog is running through the field A climber wearing a blue helmet and headlamp is attached to a rope on the rock face . A cyclist is riding a bicycle on a curved road up a hill . A dog and cat are fighting on a chair . A dog carries a leash in its mouth . A dog climbs down a black ramp A dog is running through the snow
10k images 253 classes 1 model
backpack bench chair pillow sofa Backpack armchair armchair-archviz-interior armchair-chair-leather-barcelona armchair-design-old-home-living room armchair-fabric-material-wood-wingback-chesterfield-living room-blue armchair-green armchair-house-home armchair-interior armchair-leather armchair-metal-modern-seating-black armchair-modern-couch-seating-contemporary-mozilla armchair-modern-cushion-home-interior armchair-modern-living armchair-modern-wood-ikea-historical-century-old-models-60s-fabric-20th-1960s-design-interior-history
2.5k images 12 classes 3 models
2.7k images 9 classes 2 models
3.5k images 6 classes 1 model
417 images 10 classes 1 model
160 images 4 classes 1 model
1 - 50 of 500k+
Guide: How to Count Readings with Computer Vision
With a model hosted on Roboflow like the ones above and the open source supervision Python package, you can count readings in your images and videos.
The following code snippet counts the number of readings present in an image.
To use the snippet below, you will need to run pip install roboflow supervision. Replace the project name and model name with any model trained on Universe, such as those listed above.
import supervision as sv
import roboflow
roboflow.login()
rf = roboflow.Roboflow()
# replace with the reading project you choose above
project = rf.workspace("datasetsdevelopment-ob6pc").project("academic-activities")
reading_model = project.version(13).model
results = reading_model.predict("reading.jpg").json()
readings = sv.Detections.from_roboflow(results)
# print number of readings
print(len(readings))Guide: How to Count Readings in a Zone
With a bit more code, you can count the number of reading present in a specific zone of your image or video.
The following code snippet counts the number of reading present in each frame in a video.
To use the snippet below, you will need to run pip install roboflow supervision. Replace the project name and model name with any model trained on Universe, such as those listed above.
Read our blog post on counting objects in a zone
import numpy as np
import supervision as sv
import roboflow
SOURCE_VIDEO_PATH = "reading.mp4"
TARGET_VIDEO_PATH = "reading_out.mp4"
# use https://roboflow.github.io/polygonzone/ to get the points for your shape
polygon = np.array([
# draw 50x50 box in top left corner
[0, 0],
[50, 0],
[50, 50],
[0, 50]
])
roboflow.login()
rf = roboflow.Roboflow()
# replace with the reading project you choose above
project = rf.workspace("datasetsdevelopment-ob6pc").project("academic-activities")
reading_model = project.version(13).model
# create BYTETracker instance
reading_tracker = sv.ByteTrack(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=30)
# create VideoInfo instance
video_info = sv.VideoInfo.from_video_path(SOURCE_VIDEO_PATH)
# create frame generator
generator = sv.get_video_frames_generator(SOURCE_VIDEO_PATH)
# create PolygonZone instance
zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=(video_info.width, video_info.height))
# create box annotator
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
colors = sv.ColorPalette.default()
# create instance of BoxAnnotator
zone_annotator = sv.PolygonZoneAnnotator(thickness=4, text_thickness=4, text_scale=2, zone=zone, color=colors.colors[0])
# define call back function to be used in video processing
def callback(frame: np.ndarray, index:int) -> np.ndarray:
# model prediction on single frame and conversion to supervision Detections
results = reading_model.predict(frame).json()
readings = sv.Detections.from_roboflow(results)
# show reading detections in real time
print(readings)
# tracking reading detections
readings = reading_tracker.update_with_detections(readings)
annotated_frame = box_annotator.annotate(scene=frame, detections=readings)
annotated_frame = zone_annotator.annotate(scene=annotated_frame)
# return frame with box and line annotated result
return annotated_frame
# process the whole video
sv.process_video(
source_path = SOURCE_VIDEO_PATH,
target_path = TARGET_VIDEO_PATH,
callback=callback
)